Invariant Feature with Multi-Characteristic Scales Using Gabor Filter Bank

HOU Yi; ZHOU Shi-lin; LEI Lin; ZHAO Jian

doi:10.3969/j.issn.0372-2112.2013.06.016

您当前的位置：

首页 >

文章列表页 >

Invariant Feature with Multi-Characteristic Scales Using Gabor Filter Bank

更新时间：2025-07-16

- Invariant Feature with Multi-Characteristic Scales Using Gabor Filter Bank
- Acta Electronica Sinica Vol. 41, Issue 6, Pages: 1146-1152(2013)
- 作者机构：
  
  国防科学技术大学电子科学与工程学院,湖南,长沙,410073
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China (No.61105031)
- DOI：10.3969/j.issn.0372-2112.2013.06.016
  CLC： TP391.4
- Published：2013
- 稿件说明：
移动端阅览
HOU Yi, ZHOU Shi-lin, LEI Lin, et al. Invariant Feature with Multi-Characteristic Scales Using Gabor Filter Bank[J]. Acta Electronica Sinica, 2013, 41(6): 1146-1152.
DOI：

HOU Yi, ZHOU Shi-lin, LEI Lin, et al. Invariant Feature with Multi-Characteristic Scales Using Gabor Filter Bank[J]. Acta Electronica Sinica, 2013, 41(6): 1146-1152. DOI： 10.3969/j.issn.0372-2112.2013.06.016.

摘要

提出了一种多特征尺度不变特征提取方法

简称GIFT(Gabor scale-Invariant Feature Transform).该方法首先利用2D Gabor滤波器组模拟生物视觉感知计算模型进行特征点检测

符合生物视觉感知特性

得到具物理直观性、稳健的特征点.其次采用基于Gabor核函数的特征尺度选择方法对所检测的特征点选择多个特征尺度

得到高可区分性的多特征描述子.最后

通过设计面向多特征尺度的特征匹配策略

提高特征匹配的可靠性.基于标准数据集的对比实验结果表明

GIFT方法在特征匹配率和稳健性上均优于SIFT.

Abstract

An invariant feature extraction method called GIFT(Gabor scale-Invariant Feature Transform)is proposed

which has multi-characteristic scales.Firstly

by using 2D Gabor filter bank to model the biological cognitive computational model

intuitional and robust keypoints are detected.It is accordant with vision perceptive characteristic.Secondly

multi-characteristic scales of the detected keypoints are selected based on the Gabor kernel function

and then multi-characteristic descriptors with high distinctiveness are obtained.Finally

a feature matching strategy for multi-characteristic scales is designed

which increases the reliability of feature matching.The comparison experimental results on the standard dataset show that the proposed GIFT outperforms SIFT on both feature matching rate and robustness.

关键词

Keywords

references

Views

3517

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A General Approach for Extracting Affine Invariant Regions

Multi-directional and Multi-scale Gabor Feature Representation and Its Matching Algorithm

Related Author

雷琳

王壮

粟毅

CAI Hong-ping

LEI Lin

CHEN Tao

SU Yi

ZHOU De-long

Related Institution

College of Computer Science and Technology, Zhejiang University of Technology

School of Design, Zhejiang University of Technology

College of Computer Science and Technology Zhejiang University of Technology Hangzhou Zhejiang China

School of Design Zhejiang University of Technology Hangzhou Zhejiang China

⁰